
FLUX.1 [dev] Variants: 5
The open-weights FLUX workhorse, sharper and more faithful to long prompts than schnell.
No matches. Try “video”, “FLUX” or “webhooks”.
Loading models…

The open-weights FLUX workhorse, sharper and more faithful to long prompts than schnell.

Precise local edits from one reference image, such as changing colors, adding objects or rewriting text.
Black Forest Labs' video model, 5 to 20 second clips with sound at 720p or 1080p.
Turns one portrait and a voice track into a talking, gesturing avatar video.
Topaz Labs' image upscaler with face recovery, denoise and sharpening, up to 4x.
Clean, commercially safe background removal for products and people.
No models match these filters
Clear filtersText-only chat LLM with switchable reasoning trace and up to 20,000 generated tokens
nvidia/nemotron-3-nano-omni/audioSpeech to Text
$0.01 / 1000 tokenstypical run ≈ $0.01
Integrate
nvidia/nemotron-3-nano-omniLLM
≈ $0.01
Integrate
nvidia/nemotron-3-nano-omni/videoVision
$0.006 / 1000 tokenstypical run ≈ $0.012
Integrate
nvidia/nemotron-3-nano-omni/visionVision
≈ $0.018
Integrate